An integrated circuit board production optimization method and system based on big data analysis

Abstract

The embodiment of the present application relates to the technical field of circuit production, and discloses an integrated circuit board production optimization method based on big data analysis, which comprises the following steps: after initial setting is completed, an exposure start signal is generated and transmitted to an edge processor; after the edge processor receives the exposure start signal, the thickness parameter of the copper-clad plate is obtained through a thickness gauge, the exposure imaging control is optimized according to the thickness parameter of the copper-clad plate, and after the exposure imaging control is completed, an etching start signal is generated and transmitted to the edge processor; after the edge processor receives the etching start signal, the etching effect evaluation related parameters are collected and analyzed, the etching module is optimized in real time according to the etching analysis result, and after the etching production control is completed, all optimization steps and adjustment parameters are summarized to a production optimization control log and stored in a big data cloud. The method can improve the overall production efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of circuit production, in particular to an integrated circuit board production optimization method and system based on big data analysis. BACKGROUND

[0002] At present, with the development of electronic products towards miniaturization, high performance and high reliability, the manufacturing process of integrated circuit boards as the core components of electronic products is becoming increasingly complex, and higher requirements are put forward for the precision and efficiency of the production process.

[0003] The existing integrated circuit board production optimization control is realized through data acquisition and transmission technology. Data acquisition devices are installed on production equipment, sensors, etc. to realize real-time acquisition and transmission of various data in the production process. For example, the invention patent with publication number CN115657623A discloses a flexible production line system for PCBA integrated circuit board based on cloud chain, which includes a cloud order system, a local cargo order management system, a production planning system, a raw material management system, a manufacturing management system, a line change management system, a PLC control system, an inspection system, an AGV transfer control system and a warehouse management system.

[0004] For example, the invention patent with publication number CN107357274B discloses a SMT circuit board production control device and control method, which includes a work station time setting module for setting the working time of each work station according to the actual production process; a standard time database for storing the set working time of each work station in different production processes; a work station time acquisition module for acquiring the actual working time of each work station according to the actual production process; a calling module for selecting the standard time database of the actual production process; a comparison module for comparing the actual working time of each work station acquired by the work station time acquisition module with the set working time of each work station stored in the standard time database of the actual production process selected by the selection module; and an output module for outputting the comparison result of the comparison module.

[0005] However, in the process of implementing the technical scheme of the present application embodiment, it is found that the above-mentioned technology at least has the following technical problems: in the prior art, the management of integrated circuit board production is usually only focused on data acquisition management and fixed production process flow management, and the production processes of integrated circuit boards have strong correlation. Focusing only on data acquisition management and fixed production process flow cannot make forward-looking optimization of integrated circuit board production, so the prior art has the problem of insufficient optimization precision, which leads to low yield of integrated circuit board production. SUMMARY

[0006] In view of the defects, the embodiment of the present application discloses an integrated circuit board production optimization method based on big data analysis, which can greatly improve etching precision and overall production efficiency.

[0007] The first aspect of the embodiment of the present application discloses an integrated circuit board production optimization method based on big data analysis, comprising:

[0008] When the Internet of Things gateway processor receives the integrated circuit board production signal, the related parameters affected by electrical fluctuations are collected for analysis, the light source parameters of the pattern transfer module are initially set according to the analysis results, and an exposure enable signal is generated after the initial setting is completed and is transmitted to the edge processor;

[0009] After the edge processor receives the exposure enable signal, the thickness parameters of the copper-clad plate are obtained through the thickness gauge, and the exposure imaging control is optimized according to the thickness parameters of the copper-clad plate, and an etching enable signal is generated after the exposure imaging control is completed and is transmitted to the edge processor;

[0010] After the edge processor receives the etching enable signal, the related parameters for evaluating the etching effect are collected for analysis, the etching module is optimized in real time according to the etching analysis results, and all optimization steps and adjustment parameters are summarized to the production optimization control log and stored in the big data cloud after the etching production control is completed.

[0011] As an optional implementation, in the first aspect of the embodiment of the present application, the related parameters affected by electrical fluctuations are collected for analysis, and the specific process is as follows:

[0012] The related parameters affected by electrical fluctuations include voltage sag, harmonic distortion rate, zero ground voltage and three-phase unbalance degree;

[0013] The electrical fluctuation influence coefficient is analyzed based on the related parameters affected by electrical fluctuations;

[0014] The electrical fluctuation influence coefficient is the quantitative data of the evaluation of the influence of voltage sag, harmonic distortion rate, zero ground voltage and three-phase unbalance degree on electrical fluctuations, and the specific processing process is as follows: the voltage sag, harmonic distortion rate, zero ground voltage and three-phase unbalance degree are proportionally checked with the corresponding critical value, and the proportionally checked result is coupled with the corresponding importance score to obtain the electrical fluctuation influence coefficient.

[0015] As an optional implementation, in the first aspect of the embodiment of the present application, the light source parameters of the pattern transfer module are initially set according to the analysis results, and the specific process is as follows:

[0016] The power range of the light source is obtained from the database, the power range adjustment proportion coefficient of the light source is mapped according to the electrical fluctuation influence coefficient, the power range of the light source is adjusted according to the power range adjustment proportion coefficient of the light source, the final power range of the light source is obtained, the power of the light source of the pattern transfer module is adjusted to the middle value of the final power range of the light source, and the power of the light source of the pattern transfer module is controlled to continuously be in the final power range of the light source in the exposure stage, so that the initial setting of the power of the light source of the pattern transfer module is completed.

[0017] As an optional implementation, in the first aspect of the embodiment of the present application, the thickness parameter of the copper-clad plate is obtained by the thickness gauge, and the exposure imaging control is optimized according to the thickness parameter of the copper-clad plate. The specific process is as follows:

[0018] The thickness parameter of the copper-clad plate and the required power of the photoresist layer are obtained by the thickness gauge.

[0019] The average thickness parameter of the copper-clad plate is determined, and the initial exposure light source power is determined according to the average thickness parameter and the required power of the photoresist layer.

[0020] The position information of the current exposure light source is determined, and the copper-clad plate thickness parameter of the corresponding point is determined according to the position information. The reflected light contribution and heat absorption loss are determined according to the copper-clad plate thickness parameter and the average thickness parameter.

[0021] The initial exposure light source power is dynamically adjusted according to the calculation results of the reflected light contribution and the heat absorption loss. When the calculation result is in the first interval, the initial exposure light source power is reduced. When the calculation result is in the second interval, the initial exposure light source power is not adjusted. When the calculation result is in the third interval, the initial exposure light source power is increased.

[0022] As an optional implementation, in the first aspect of the embodiment of the present application, the production optimization method further comprises:

[0023] The corresponding 3D point cloud data is determined by the laser displacement sensor.

[0024] The 3D point cloud data is processed by a plane fitting algorithm to output the corresponding fitting plane result.

[0025] The maximum vertical distance of all points to the fitting plane is calculated, and the focal length of each point is dynamically adjusted according to the maximum vertical distance and the initial focal length to compensate for the focal length deviation caused by the warping of the plate surface.

[0026] As an optional implementation, in the first aspect of the embodiment of the present application, the etching effect evaluation related parameters are collected and analyzed, and the specific process is as follows:

[0027] The evaluation-related parameters of the etching effect include etching average depth deviation, etching average line width roughness and etching average rate deviation;

[0028] The etching effect measurement coefficient is analyzed based on the evaluation-related parameters of the etching effect;

[0029] The etching effect measurement coefficient is the quantitative data of the etching average depth deviation, the etching average line width roughness and the etching average rate deviation on the evaluation of the etching effect, and the specific processing process is that the etching average depth deviation, the etching average line width roughness and the etching average rate deviation are proportionally checked with corresponding reference values, and the proportionally checked results are coupled with corresponding importance scores to obtain the etching effect measurement coefficient.

[0030] As an optional implementation, in the first aspect of the embodiment of the present application, the real-time optimization of the etching module according to the etching analysis result has the following specific process:

[0031] The etching effect measurement coefficient is coupled with the etching environment correction coefficient to obtain an etching effect correction value, the etching is optimized according to the etching effect correction value, if the etching effect correction value is greater than or equal to an etching effect correction threshold value, it is judged that the etching process does not need to be optimized, a log generation control signal is sent to the edge processor, if the etching effect correction value is less than the etching effect correction threshold value, the etching liquid flow of the etching process is adjusted according to the absolute difference between the etching effect correction value and the etching effect correction threshold value, after the adjustment of the etching liquid flow, if the etching effect correction value analyzed again is less than or equal to the original etching effect correction value, it is judged that the integrated circuit board is a defective product, and an alarm is sent;

[0032] If the etching effect correction value analyzed again is greater than the original etching effect correction value and still less than the etching effect correction threshold value, the etching liquid flow of the etching process is readjusted until the etching effect correction value is greater than or equal to the etching effect correction threshold value;

[0033] If the etching liquid flow reaches the maximum value of the specified range of the etching liquid flow and at the same time the etching effect correction value is still less than the etching effect correction threshold value, the etching liquid pressure is adjusted, the increase amount of the etching liquid pressure is mapped according to the absolute difference between the etching effect correction value and the etching effect correction threshold value, and the etching liquid pressure is automatically adjusted according to the increase amount of the etching liquid pressure.

[0034] The second aspect of the embodiment of the present application discloses an integrated circuit board production optimization system based on big data analysis, which comprises:

[0035] The collecting module is used for collecting and analyzing the parameters related to the electrical fluctuation influence when the integrated circuit board production signal is received by the Internet of Things gateway processor, and initially setting the light source parameters of the pattern transfer module according to the analysis result, and generating an exposure enable signal and transmitting the exposure enable signal to the edge processor after the initial setting is completed.

[0036] The exposure module is used for acquiring the thickness parameter of the copper-clad plate by a thickness gauge after the edge processor receives the exposure enable signal, and optimizing the exposure imaging control according to the thickness parameter of the copper-clad plate, and generating an etching enable signal and transmitting the etching enable signal to the edge processor after the exposure imaging control is completed.

[0037] The etching module is used for collecting and analyzing the parameters related to the etching effect evaluation after the edge processor receives the etching enable signal, and optimizing the etching module in real time according to the etching analysis result, and summarizing all the optimization steps and adjustment parameters to a production optimization control log and storing the production optimization control log in the big data cloud after the etching production control is completed.

[0038] The third aspect of the embodiment of the present application discloses an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor invokes the executable program code stored in the memory, and is used for executing the integrated circuit board production optimization method based on big data analysis disclosed in the first aspect of the embodiment of the present application.

[0039] The fourth aspect of the embodiment of the present application discloses a computer readable storage medium storing a computer program, wherein the computer program enables a computer to execute the integrated circuit board production optimization method based on big data analysis disclosed in the first aspect of the embodiment of the present application.

[0040] Compared with the prior art, the embodiment of the present application has the following beneficial effects:

[0041] The integrated circuit board production optimization method based on big data analysis in the embodiment of the present application can collect and analyze related parameters in real time in each link in the production process, such as electrical fluctuation parameters, copper-clad plate thickness parameters, etching effect evaluation parameters, etc. Based on these real-time data, abnormal conditions in the production process can be found in time, and adjustments can be made quickly to ensure the stability and consistency of the production process and reduce the production interruption caused by equipment failure or parameter misadjustment. BRIEF DESCRIPTION OF DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.Figure 1 is a flowchart of the integrated circuit board production optimization method based on big data analysis disclosed by the embodiments of the present application;

[0044] Figure 2 is a flowchart of the light source power adjustment disclosed by the embodiments of the present application;

[0045] Figure 3 is a flowchart of the focal length adjustment disclosed by the embodiments of the present application; Figure 4 is a structural schematic diagram of an integrated circuit board production optimization system based on big data analysis provided by the embodiments of the present application;

[0046] Figure 5 is a structural schematic diagram of an electronic device provided by the embodiments of the present application. DETAILED DESCRIPTION

[0047] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0048] It should be noted that the terms "first", "second", "third", "fourth" and the like in the specification and claims of the present application are used to distinguish different objects, rather than to describe a specific order. The terms "include" and "have" and any variations thereof in the embodiments of the present application are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units need not be limited to those clearly listed steps or units, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0049] Embodiment one

[0050] Please refer to Figure 1 , Figure 1It is the flow chart of the integrated circuit board production optimization method based on big data analysis disclosed by the embodiment of the application. Among them, the execution subject of the method described in the embodiment of the application is composed of software or / and hardware, which can receive relevant information through wired or / and wireless mode, and can send certain instructions. Of course, it can also have certain processing function and storage function. The execution subject can control multiple devices, such as remote physical servers or cloud servers and related software, or local host or server and related software for related operation of the device placed in some place. In some scenarios, it can also control multiple storage devices, which can be placed in the same place or different places. As shown in Figure 1 The integrated circuit board production optimization method based on big data analysis includes the following steps:

[0051] S101: When the integrated circuit board production signal is received by the Internet of Things gateway processor, collect and analyze the related parameters affected by electrical fluctuation, set the light source parameters of the pattern transfer module according to the analysis results, and generate an exposure enable signal after the initial setting is completed and transmit it to the edge processor;

[0052] S102: After the edge processor receives the exposure enable signal, the thickness parameter of the copper-clad plate is obtained by the thickness gauge, and the exposure imaging control is optimized according to the thickness parameter of the copper-clad plate, and the etching enable signal is generated after the exposure imaging control is completed and transmitted to the edge processor;

[0053] S103: After the edge processor receives the etching enable signal, collect and analyze the related parameters for evaluating the etching effect, optimize the etching module in real time according to the etching analysis results, and after the etching production control is completed, all optimization steps and adjustment parameters are summarized to the production optimization control log and stored in the big data cloud.

[0054] The embodiment of the application provides an integrated circuit board production optimization control method and system based on big data analysis, which solves the problem of insufficient integrated circuit board production optimization rate in the prior art. By collecting and analyzing the related parameters affected by electrical fluctuation, the light source power of the pattern transfer module is initially set according to the analysis results, and the effect of improving the integrated circuit board production optimization rate is achieved.

[0055] The technical solution in the embodiment of the present application is to solve the above-mentioned problem of insufficient production good rate of integrated circuit boards, and the general idea is as follows: after receiving the production signal by the Internet of Things gateway processor, the electrical fluctuation influence parameter is analyzed and the light source power of the graphic transfer module is initially set, and then the exposure enable signal is sent to the edge processor. The edge processor optimizes the exposure production control accordingly, and generates the etching enable signal after ending. After receiving the signal again, the edge processor collects the etching effect evaluation parameter and optimizes the etching module in real time, and finally all the optimization steps and parameters are summarized to the production optimization control log and stored in the big data cloud, so as to improve the production good rate of integrated circuit boards.

[0056] In the embodiment of the present application, the Internet of Things gateway processor is the key hub connecting the Internet of Things devices and the backend system, collects production signals and electrical fluctuation parameters, converts them into unified format data after preliminary processing, transmits them to the big data analysis system through the network, cleans, de-duplicates and normalizes the original data, improves the data quality, reduces invalid data and noise, reduces the processing burden of the big data platform, provides rich, comprehensive and structured data basis for big data analysis, transmits the data to the big data cloud for deep analysis, reduces the delay of data transmission, improves the real-time performance and response speed of the system, and the Internet of Things gateway processor combines edge computing technology to realize edge and distributed computing of data processing, and forms a collaborative working mechanism with the analysis of the big data cloud.

[0057] Specifically, the Internet of Things gateway processor combines edge computing technology to realize edge and distributed computing of data processing, and collaborates with the cloud big data analysis system to fully exert the advantages of both and improve system efficiency. The edge server refers to an intermediate device between the data source and the cloud platform, which undertakes data processing, analysis and control tasks.

[0058] The production optimization control log is a document that records various optimization operations, parameter adjustments, device states and production conditions in the production process in detail, and the document content includes optimization steps, adjustment parameters, time stamps, operator or system identifier, production batch, device number, etc. The big data cloud refers to a service mode that provides computing resources, storage resources, software services, etc. through the Internet, and the production optimization control log can be transmitted to the big data cloud for storage through the network.

[0059] The embodiment of the present application can make the light source parameters more accurate by collecting the parameters related to the influence of electrical fluctuations to initially set the light source parameters of the pattern transfer module, thereby improving the accuracy of pattern transfer and laying a good foundation for subsequent processes. The exposure imaging control can be optimized according to the thickness parameters of the copper-clad plate, which can ensure the quality of exposure imaging and reduce image deviation and other problems caused by thickness differences. The etching module is optimized in real time, which can adjust the etching process in time according to the etching effect evaluation parameters, avoid over-etching or under-etching, improve the etching precision, and thus improve the overall quality of the integrated circuit board.

[0060] During the production process, relevant parameters can be collected and analyzed in real time at each link, such as electrical fluctuation parameters, copper-clad plate thickness parameters, and etching effect evaluation parameters. Based on these real-time data, abnormal conditions in the production process can be found in time, and adjustments can be made quickly to ensure the stability and consistency of the production process and reduce production interruptions caused by equipment failure or parameter misadjustment.

[0061] All optimization steps and adjustment parameters are summarized in the production optimization control log and stored in the big data cloud, which facilitates the traceability of the production process. When quality problems occur or further optimization of the production process is needed, the log can be consulted to understand the specific operation and parameter adjustment of each link, providing detailed data support for analyzing the causes of problems and developing improvement measures. At the same time, the accumulated large amount of production data can also be used for subsequent big data analysis to explore potential optimization space and continuously improve production processes and product quality.

[0062] The embodiment of the present application reduces the rate of defective products and rework rate through real-time optimization and precise control, thereby improving production efficiency and shortening production cycle. In addition, reasonable parameter setting and optimized production process can also reduce the consumption of raw materials and energy and reduce production costs.

[0063] More preferably, the collection of parameters related to the influence of electrical fluctuations for analysis has the following specific process:

[0064] The parameters related to the influence of electrical fluctuations include voltage sag, harmonic distortion rate, zero-ground voltage, and three-phase imbalance degree.

[0065] The electrical fluctuation influence coefficient is analyzed based on the parameters related to the influence of electrical fluctuations.

[0066] The electrical fluctuation influence coefficient is the quantitative data of the common influence of voltage sag, harmonic distortion rate, zero-ground voltage, and three-phase imbalance degree on electrical fluctuations. The specific processing process is as follows: the voltage sag, harmonic distortion rate, zero-ground voltage, and three-phase imbalance degree are proportionally checked with the corresponding critical values, and the proportionally checked results are coupled with the corresponding importance scores to obtain the electrical fluctuation influence coefficient.

[0067] The embodiment of the present application converts the originally abstract electrical fluctuation influence into specific quantitative data by proportionally checking each parameter with the corresponding critical value and coupling processing the electrical fluctuation influence coefficient by combining the importance score. This quantitative method can uniformly measure electrical fluctuation influences of different degrees and types, facilitating objective comparison and analysis, and improving the scientificity and reliability of the evaluation results.

[0068] Compared with empirical setting, the light source parameter of the pattern transfer module is set based on the quantified electrical fluctuation influence coefficient, which has more data support. The light source parameter can be adjusted according to the actual influence degree of the electrical fluctuation, so that the light source parameter is adapted to the current electrical environment, the deviation of pattern transfer caused by the electrical fluctuation is reduced, and the pattern transfer quality is further improved. The parameter analysis process forms a clear calculation logic and quantitative results, and these data can be included in the production optimization control log. When the production process is traced back or improved in the future, the specific quantitative situation of the electrical fluctuation influence and the basis for setting the light source parameter can be clearly understood, which provides reference quantitative data support for continuously optimizing the production process.

[0069] More preferably, the light source parameter of the pattern transfer module is initially set according to the analysis result, and the specific process is as follows:

[0070] The power range of the light source parameter is obtained from the database, the power range adjustment proportion coefficient of the light source is mapped according to the electrical fluctuation influence coefficient, the power range of the light source is adjusted according to the power range adjustment proportion coefficient of the light source, the final power range of the light source is obtained, the light source power of the pattern transfer module is adjusted to the middle value of the final power range of the light source, and the light source power of the pattern transfer module is controlled to be continuously in the final power range of the light source during the exposure stage, thereby completing the initial setting of the light source power of the pattern transfer module.

[0071] The embodiment of the present application maps the power range adjustment proportion coefficient based on the electrical fluctuation influence coefficient, and then adjusts the power range of the light source, so that the light source parameter setting is accurately corresponding to the fluctuation condition of the current electrical environment. This dynamic adaptation mechanism avoids the mismatching problem of fixed parameter setting in electrical fluctuation, and provides a basic guarantee for the quality of pattern transfer. The complete steps from obtaining the reference range from the database, calculating the adjustment proportion, determining the final range to setting the middle value are clearly defined in the process, so that the light source parameter setting process is standardized and normalized. This not only reduces the subjectivity and error of manual operation, but also facilitates the understanding and execution of production personnel, and improves the controllability of the production process.

[0072] More preferably, as shown in Figure 2 The thickness parameter of the copper-clad plate is obtained by the thickness gauge, and the exposure imaging control is optimized according to the thickness parameter of the copper-clad plate, and the specific process is as follows:

[0073] S1021: Obtain the thickness parameter of the copper-clad plate and the required power of the photoresist layer by a thickness gauge;

[0074] S1022: Determine the average thickness parameter of the copper-clad plate, and determine the corresponding initial exposure light source power according to the average thickness parameter and the required power of the photoresist layer;

[0075] S1023: Determine the position information of the current exposure light source, and determine the copper plate thickness parameter of the corresponding point according to the position information, and determine the corresponding reflected light contribution and heat absorption loss according to the copper plate thickness parameter and the average thickness parameter;

[0076] S104: Dynamically adjust the initial exposure light source power according to the calculation results of the reflected light contribution and the heat absorption loss; when the calculation result is in the first interval, the initial exposure light source power is reduced; when the calculation result is in the second interval, the initial exposure light source power is not adjusted, and when the calculation result is in the third interval, the initial exposure light source power is increased.

[0077] In PCB manufacturing, the thickness of copper foil is not absolutely constant, and its actual thickness will vary significantly due to material selection, process fluctuation and design requirements. The core role of LDI (laser direct imaging) is to have a photochemical reaction with the photoresist layer, and the copper thickness itself does not directly participate in the process. However, the copper thickness difference will significantly affect the LDI process effect through the following indirect mechanisms: different copper thicknesses cause changes in the thermal dissipation of laser energy in the copper layer; although the target of LDI is the photoresist layer, the copper thickness directly affects the cross-linking effect of the photoresist through the thermodynamic-optical coupling mechanism. Based on this, it is realized in the embodiments of the present application that a dynamic matching model of copper thickness-LDI parameters must be established for PCB manufacturing to achieve more accurate dynamic adjustment.

[0078] Specifically, the initial exposure power is determined in combination with the average thickness of the copper-clad plate and the required power of the photoresist layer, and then the reflected light contribution and heat absorption loss are calculated according to the difference between the thickness of the specific point and the average thickness, thereby realizing fine power adjustment from the whole to the local. This hierarchical optimization mechanism enables the exposure power to adapt to both the overall characteristics and the local differences of the copper-clad plate, greatly improving the matching accuracy of exposure imaging and material characteristics.

[0079] By associating the position information with the point thickness parameter, the power is dynamically adjusted according to the thickness difference of different regions (such as power compensation for abnormal thickness regions through reflected light and heat loss calculation), effectively offsetting the exposure effect difference caused by uneven thickness of the copper-clad plate. This reduces the problem of local overexposure or underexposure, and significantly improves the overall uniformity of integrated circuit board pattern transfer.

[0080] In the embodiment of the present application, three interval adjustment strategies (reduction, maintenance, and promotion) are set, so that the exposure system can make targeted adjustments according to real-time calculation results, rather than using a fixed power mode. This dynamic response mechanism can respond to fluctuations in material properties in the production process in a timely manner, ensuring the stability of exposure quality. The technical solution realizes precise control and optimization of the LDI exposure process through a copper thickness-photoresist coupling energy control model.

[0081] More preferably, the production optimization method further comprises:

[0082] The corresponding 3D point cloud data is determined by a laser displacement sensor.

[0083] A plane fitting algorithm is used to process the 3D point cloud data to output the corresponding fitting plane result.

[0084] The maximum vertical distance of all points to the fitting plane is calculated, and the focal length of each point is dynamically adjusted according to the maximum vertical distance and the initial focal length to compensate for the focal length deviation caused by the warping of the plate surface.

[0085] The scheme of the embodiment of the present application uses a laser displacement sensor to obtain 3D point cloud data of the copper-clad plate, establishes a reference plane through a plane fitting algorithm, and calculates the maximum vertical distance of each point to the reference plane, which can quantitatively represent the warping degree and spatial distribution of the plate surface. Based on this, the focal length of each point is dynamically adjusted to specifically offset the focal length deviation caused by the unevenness of the plate surface, solving the problem of local imaging blur that often occurs on warped plates with traditional fixed focal length.

[0086] Through point-by-point dynamic focal length compensation, it ensures that each point on the surface of the copper-clad plate can obtain the best focusing effect. This significantly improves the detail restoration degree of pattern transfer, especially for fine line patterns on high-precision integrated circuit boards. Traditional production equipment has high requirements for the flatness of copper-clad plates, but this scheme reduces the dependence on the flatness of raw materials through an active compensation mechanism, and can handle more warped plates, improving material utilization and reducing the increase in costs caused by strict material selection.

[0087] In the traditional exposure process, the uneven thickness of the copper-clad plate will cause differences in light absorption (more heat absorption for thick copper plate, different light reflectivity), and the plate warping will cause local focal length deviation, both of which will cause uneven distribution of exposure energy on the plate surface, resulting in problems such as blurred line edges, inconsistent line widths, and local overexposure / underexposure. In the embodiments of the present application, through copper plate thickness compensation (dynamic adjustment of exposure power to offset the light absorption / reflection deviation caused by thickness difference) and warping compensation (point-by-point adjustment of focal length to ensure focusing clarity), the exposure energy can be accurately applied to the photoresist layer at the microscopic level, ensuring the line width accuracy, edge flatness and pattern consistency of the pattern transfer, and fundamentally solving the problem of unstable exposure quality caused by material property fluctuations.

[0088] The traditional process deals with material fluctuations by selecting qualified materials (passively avoiding defects) or setting fixed redundant parameters (such as increasing exposure power to cover thickness deviation). The essence is a compromise solution that sacrifices efficiency / precision. The scheme of the embodiments of the present application creatively combines three-dimensional shape perception (laser point cloud detection warping) with material property quantification (thickness parameter and photoresist required power correlation), establishes a closed-loop control of defect detection-data modeling-dynamic adjustment, and actively offsets the material defects, rather than passively accepting them, which is a fundamental breakthrough in process concept.

[0089] The scheme of the embodiments of the present application converts copper plate thickness difference into light energy correction coefficient (combining reflected light contribution and heat absorption loss), converts warping deviation into spatial focal length compensation value (based on the vertical distance from point cloud to fitting plane), and realizes the coordinated optimization of multiple parameters through interval adjustment strategy (such as three-interval power adjustment for thickness compensation, point-by-point focal length adaptation for warping compensation). This idea of coupling analysis of geometric shape (warping) and physical properties (thickness-light interaction) breaks through the limitations of traditional single parameter adjustment and meets the stringent requirements of high-precision integrated circuit boards for exposure effect.

[0090] More preferably, the collection of etching effect evaluation related parameters is analyzed, and the specific process is as follows:

[0091] The etching effect evaluation related parameters include etching average depth deviation, etching average line width roughness and etching average rate deviation;

[0092] The etching effect evaluation related parameters include etching average depth deviation, etching average line width roughness and etching average rate deviation;

[0093] The etching effect measurement coefficient is a quantitative data of the etching average depth deviation, the etching average line width roughness and the etching average rate deviation for evaluating the etching effect, and the specific processing process is: the etching average depth deviation, the etching average line width roughness and the etching average rate deviation are proportionally checked with the corresponding reference values, and the proportionally checked results are coupled with the corresponding importance scores to obtain the etching effect measurement coefficient.

[0094] In the embodiment, the specific method for obtaining the etching effect measurement coefficient is:

[0095]

[0096] γ1+γ2+γ3=1;

[0097] In the formula, YUM represents the etching effect measurement coefficient for evaluating the pattern effect after etching, VHJ represents the etching average depth deviation, VHJ0 represents the reference value of the etching average depth deviation, γ1 represents the importance score of the etching average depth deviation, RYN represents the etching average line width roughness, RYN0 represents the reference value of the etching average line width roughness, γ2 represents the importance score of the etching average line width roughness, KLF represents the etching average rate deviation, KLF0 represents the reference value of the etching average rate deviation, and γ3 represents the importance score of the etching average rate deviation.

[0098] The reference values of the etching average depth deviation, the etching average line width roughness and the etching average rate deviation refer to the reference values of the etching average depth deviation, the etching average line width roughness and the etching average rate deviation, which can be obtained from a database. The etching average depth deviation refers to the average value of the deviation between the etching depth and the standard etching depth within a predefined time, which can be measured by a high-precision surface analysis instrument.

[0099] The etching average line width roughness refers to the average value of the etching line width roughness within a predefined time, which can be measured by a high-precision surface analysis instrument on the etched line width. The etching average rate deviation refers to the deviation between the average value of the etching rate within a predefined time and the reference value, which can be obtained from a database. The etching process can be detected in real time to detect the etching condition of the material. If the deviation between the etching speed and the reference value is too large, the etching speed is too fast, which will make the etching depth and width exceed the expectation, resulting in the line width of the circuit being narrowed or broken, affecting the normal connection of the circuit. If the etching speed is too slow, the line width will be widened, increasing the risk of short circuit between adjacent circuits, reducing the precision of pattern transfer, and failing to meet the design requirements of fine patterns.

[0100] When it is observed that the line width roughness is large after etching, it means that there is a deviation in the etching depth, and if the etching rate is different at different time periods or different positions, then the etching depth will be different at the same time, and the etching rate that is too fast can cause the reaction to be too violent, making it difficult to accurately control the etching process, thereby increasing the line width roughness.

[0101] When the system is running, a mapping table of importance scores is obtained through the database, for example, the corresponding importance scores are extracted according to the current etching average depth deviation, etching average line width roughness and etching average rate deviation, such as the importance score of the etching average depth deviation, the importance score of the etching average line width roughness and the importance score of the etching average rate deviation. This mapping table defines a clear set of association rules, which converts the specific values of the etching average depth deviation, etching average line width roughness and etching average rate deviation into their corresponding importance scores. Under this mechanism, whether it is to achieve one-to-one accurate matching or multiple parameters converging into a single weight many-to-one relationship, the dynamic acquisition of importance scores can be effectively realized.

[0102] More preferably, the etching module is optimized in real time according to the etching analysis result, and the specific process is as follows:

[0103] S1031: coupling the etching effect measurement coefficient and the etching environment correction coefficient to obtain an etching effect correction value, optimizing the etching according to the etching effect correction value, if the etching effect correction value is greater than or equal to the etching effect correction threshold, it is judged that the etching process does not need to be optimized, and a log generation control signal is sent to the edge processor, if the etching effect correction value is less than the etching effect correction threshold, the etching liquid flow of the etching process is adjusted according to the absolute difference between the etching effect correction value and the etching effect correction threshold, after the adjustment of the etching liquid flow, if the etching effect correction value analyzed again is less than or equal to the original etching effect correction value, it is judged that the integrated circuit board is a defective product, and an alarm is sent;

[0104] S1032: if the etching effect correction value analyzed again is greater than the original etching effect correction value and still less than the etching effect correction threshold, the etching liquid flow of the etching process is adjusted again until the etching effect correction value is greater than or equal to the etching effect correction threshold;

[0105] S1033: if the etching liquid flow reaches the maximum value of the specified range of the etching liquid flow and at the same time the etching effect correction value is still less than the etching effect correction threshold, the etching liquid pressure is adjusted, the increase amount of the etching liquid pressure is mapped according to the absolute difference between the etching effect correction value and the etching effect correction threshold, and the etching liquid pressure is automatically adjusted according to the increase amount of the etching liquid pressure.

[0106] In the embodiment, the etching effect measurement coefficient is coupled with the etching environment correction coefficient, and the coupling process is as follows: the etching effect measurement coefficient is multiplied by the etching environment correction coefficient to obtain an etching effect correction value.

[0107] The etching liquid flow is adjusted according to the absolute difference between the etching effect correction value and the etching effect correction threshold, and the specific process is as follows: the adjustment amount of the etching liquid flow is mapped according to the absolute difference between the etching effect correction value and the etching effect correction threshold, and the etching liquid flow is automatically adjusted according to the adjustment amount of the etching liquid flow.

[0108] The etching liquid flow is controlled by the adjustment amount of the etching liquid flow, and the amplified etching liquid flow is equal to the adjustment amount of the etching liquid flow.

[0109] The adjustment amount of the etching liquid flow is mapped according to the absolute difference between the etching effect correction value and the etching effect correction threshold, and the specific process is as follows: a mapping set between the absolute difference and the adjustment amount of the etching liquid flow is obtained from a database, the absolute difference between the existing etching effect correction value and the etching effect correction threshold is input into the mapping set, and the adjustment amount of the etching liquid flow is obtained. The increase amount of the etching liquid pressure is mapped according to the absolute difference between the etching effect correction value and the etching effect correction threshold, and the specific process is as follows: a mapping set between the absolute difference and the increase amount of the etching liquid pressure is obtained from a database, the absolute difference between the existing etching effect correction value and the etching effect correction threshold is input into the mapping set, and the increase amount of the etching liquid pressure is obtained.

[0110] The integrated circuit board production optimization method based on big data analysis in the embodiment can collect relevant parameters in real time and analyze them in each link in the production process, such as electrical fluctuation parameters, copper-clad plate thickness parameters, and etching effect evaluation parameters. Based on these real-time data, abnormal conditions in the production process can be found in time, and adjustments can be made quickly to ensure the stability and consistency of the production process and reduce production interruptions caused by equipment failure or parameter misadjustment.

[0111] Embodiment two

[0112] Please refer to Figure 4 , Figure 4 is a structural schematic diagram of the integrated circuit board production optimization system based on big data analysis disclosed in the embodiment. As Figure 4 shown, the integrated circuit board production optimization system based on big data analysis can include:

[0113] The collection module 21 is used for collecting the parameters related to the influence of electrical fluctuation for analysis when the integrated circuit board production signal is received by the Internet of Things gateway processor, and the light source parameters of the pattern transfer module are initially set according to the analysis result, and an exposure enable signal is generated and transmitted to the edge processor after the initial setting is completed;

[0114] The exposure module 22 is used for acquiring the thickness parameter of the copper-clad plate by a thickness gauge after the edge processor receives the exposure enable signal, and the exposure imaging control is optimized according to the thickness parameter of the copper-clad plate, and an etching enable signal is generated and transmitted to the edge processor after the exposure imaging control is completed.

[0115] The etching module 23 is used for collecting the parameters related to the etching effect evaluation for analysis after the edge processor receives the etching enable signal, and the etching module is optimized in real time according to the etching analysis result, and all optimization steps and adjustment parameters are summarized to the production optimization control log and stored in the big data cloud after the etching production control is completed.

[0116] The integrated circuit board production optimization method based on big data analysis in the embodiment can collect related parameters in real time and perform analysis in each link in the production process, such as electrical fluctuation parameters, copper-clad plate thickness parameters, etching effect evaluation parameters and the like. Based on these real-time data, abnormal conditions in the production process can be found in time, and adjustments can be made quickly to ensure the stability and consistency of the production process and reduce production interruptions caused by equipment failure or parameter misadjustment.

[0117] Embodiment three

[0118] Please refer to Figure 5 , Figure 5 is a structural schematic diagram of an electronic device disclosed in the embodiment. The electronic device can be a computer, a server and the like, and of course, under certain circumstances, it can also be a mobile phone, a tablet computer, a monitoring terminal and the like intelligent device, and an image acquisition device with processing function. As shown in the figure, Figure 5 The electronic device can include:

[0119] The memory 510 stores executable program codes;

[0120] The processor 520 is coupled with the memory 510;

[0121] The processor 520 calls the executable program codes stored in the memory 510 to execute part or all of the steps of the integrated circuit board production optimization method based on big data analysis in the embodiment.

[0122] The embodiment of the present application discloses a computer readable storage medium which stores a computer program, wherein the computer program makes a computer execute part or all steps in the integrated circuit board production optimization method based on big data analysis in the embodiment one.

[0123] The embodiment of the present application also discloses a computer program product, wherein when the computer program product runs on a computer, the computer program product makes the computer execute part or all steps in the integrated circuit board production optimization method based on big data analysis in the embodiment one.

[0124] The embodiment of the present application also discloses an application publishing platform, wherein the application publishing platform is used for publishing a computer program product, wherein when the computer program product runs on a computer, the computer program product makes the computer execute part or all steps in the integrated circuit board production optimization method based on big data analysis in the embodiment one.

[0125] In various embodiments of the present application, it should be understood that the size of the serial number of the processes does not mean the inevitable sequence of execution, and the execution sequence of the processes should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiment of the present application.

[0126] The units described as separate components can or can not be physically separated, and the components displayed as units can or can not be physical units, that is, they can be located in one place, or they can be distributed to multiple network units. According to actual needs, part or all of the units can be selected to achieve the purpose of the embodiment of the present application.

[0127] In addition, each functional unit in the embodiments of the present application can be integrated in one processing unit, or each unit can exist physically independently, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0128] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer accessible memory. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product, and the computer software product is stored in a memory, including a plurality of parts or all steps of the method executed by a computer device (which can be a personal computer, a server or a network device, etc., and specifically can be a processor in the computer device) to execute the embodiments of the present application.

[0129] In the embodiments provided in the present application, it should be understood that "B corresponding to A" means that B is associated with A, and B can be determined according to A. However, it should also be understood that the determination of B according to A does not mean that B is determined only according to A, but B can also be determined according to A and / or other information.

[0130] A person of ordinary skill in the art can understand that part or all of the steps in the various methods of the embodiments can be completed by instructing the relevant hardware by a program, and the program can be stored in a computer readable storage medium, including Read-Only Memory (ROM), Random Access Memory (RAM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), One-time Programmable Read-Only Memory (OTPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Compact Disc Read-Only Memory (CD-ROM) or other optical disk memories, magnetic disk memories, magnetic tape memories, or any other computer readable medium capable of carrying or storing data.

[0131] The above discloses the integrated circuit board production optimization method, system, electronic equipment and storage medium based on big data analysis in the embodiments of the present application in detail. The principle and implementation mode of the present application are described by applying specific examples in this paper. The above embodiment is only used to help understand the method and core idea of the present application; at the same time, for the general technical personnel in the art, according to the idea of the present application, the specific implementation mode and application range will be changed, and the above description should not be understood as the limitation of the present application.

Claims

1. A method for optimizing production of integrated circuit boards based on big data analysis, characterized by, The application relates to an integrated circuit board production signal receiving method of an Internet of Things gateway processor. When the integrated circuit board production signal is received by the Internet of Things gateway processor, the related parameters affected by electrical fluctuation are collected for analysis, the light source parameters of a pattern transfer module are initially set according to the analysis results, and an exposure enabling signal is generated after the initial setting and is transmitted to an edge processor; the related parameters affected by electrical fluctuation are collected for analysis, and the specific process is as follows: The related parameters affected by electrical fluctuation include voltage sag, harmonic distortion rate, zero-ground voltage and three-phase unbalance degree. The related parameters affected by electrical fluctuation are analyzed to obtain an electrical fluctuation influence coefficient. The electrical fluctuation influence coefficient is quantitative data of evaluation of the influence of voltage sag, harmonic distortion rate, zero-ground voltage and three-phase unbalance degree on electrical fluctuation, and the specific processing process is as follows: the voltage sag, harmonic distortion rate, zero-ground voltage and three-phase unbalance degree are proportionally checked with corresponding critical values, the proportionally checked results are coupled with corresponding importance scores to obtain the electrical fluctuation influence coefficient. The light source parameters of the pattern transfer module are initially set according to the analysis results, and the specific process is as follows: The power range of the light source parameters is obtained from a database, the power range adjustment proportion coefficient of the light source is mapped according to the electrical fluctuation influence coefficient, the power range of the light source is adjusted according to the power range adjustment proportion coefficient of the light source, the final power range of the light source is obtained, the light source power of the pattern transfer module is adjusted to the middle value of the final power range of the light source, the light source power of the pattern transfer module is controlled to continuously be in the final power range of the light source in the exposure stage, and the initial setting of the light source power of the pattern transfer module is completed. After the edge processor receives the exposure enabling signal, the thickness parameter of the copper-clad plate is obtained through a thickness gauge, the exposure imaging control is optimized according to the thickness parameter of the copper-clad plate, and an etching enabling signal is generated after the exposure imaging control is completed and is transmitted to the edge processor. After the edge processor receives the etching enabling signal, the etching effect evaluation related parameters are collected for analysis, the etching module is optimized in real time according to the etching analysis results, and all the optimization steps and adjustment parameters are summarized to a production optimization control log and are stored in a big data cloud after the etching production control is completed.

2. The big data analytics based integrated circuit board production optimization method of claim 1, wherein, The thickness parameter of the copper-clad plate is obtained through the thickness gauge, and the exposure imaging control is optimized according to the thickness parameter of the copper-clad plate. The thickness parameter of the copper-clad plate is obtained through the thickness gauge, and the exposure imaging control is optimized according to the thickness parameter of the copper-clad plate. The average thickness parameter of the copper-clad plate is determined, the corresponding initial exposure light source power is determined according to the average thickness parameter and the demand power of the photoresist layer, the position information of the current exposure light source is determined, the copper plate thickness parameter of the corresponding point is determined according to the position information, the reflection light contribution and the heat absorption loss of the corresponding point are determined according to the copper plate thickness parameter and the average thickness parameter, and the initial exposure light source power is dynamically adjusted according to the calculation results of the reflection light contribution and the heat absorption loss. When the calculation result is in the first interval, the initial exposure light source power is reduced; when the calculation result is in the second interval, the initial exposure light source power is not adjusted; and when the calculation result is in the third interval, the initial exposure light source power is increased. ​ 3. The big data analytics based integrated circuit board production optimization method of claim 1, wherein, The production optimization method further comprises: determining the corresponding 3D point cloud data by a laser displacement sensor; processing the 3D point cloud data by a plane fitting algorithm to output the corresponding fitting plane result; calculating the maximum vertical distance of all points to the fitting plane, and dynamically adjusting the focal length of each point according to the maximum vertical distance and the initial focal length to compensate for the focal length deviation caused by the plate warping.

4. The big data analytics based integrated circuit board production optimization method of claim 1, wherein, The collected etching effect evaluation related parameters are analyzed, and the specific process is as follows: The etching effect evaluation related parameters include etching average depth deviation, etching average line width roughness and etching average rate deviation; The etching effect evaluation related parameters are analyzed based on the etching effect evaluation related parameters to obtain the etching effect measurement coefficient. The etching effect measurement coefficient is the quantitative data of the etching effect evaluation of the etching average depth deviation, etching average line width roughness and etching average rate deviation, and the specific processing process is: the etching average depth deviation, etching average line width roughness and etching average rate deviation are proportionally checked with the corresponding reference value, and the proportionally checked result is coupled with the corresponding importance score to obtain the etching effect measurement coefficient.

5. The big data analytics based integrated circuit board production optimization method of claim 1, wherein, The etching module is optimized in real time according to the etching analysis result, and the specific process is as follows: The etching effect measurement coefficient is coupled with the etching environment correction coefficient to obtain the etching effect correction value, and the etching is optimized according to the etching effect correction value. If the etching effect correction value is greater than or equal to the etching effect correction threshold, it is judged that the etching process does not need to be optimized, and a log generation control signal is sent to the edge processor. If the etching effect correction value is less than the etching effect correction threshold, the etching liquid flow of the etching process is adjusted according to the absolute difference between the etching effect correction value and the etching effect correction threshold. After the etching liquid flow is adjusted, if the etching effect correction value analyzed again is less than or equal to the original etching effect correction value, it is judged that the integrated circuit board is a defective product, and an alarm is sent. If the etching effect correction value analyzed again is greater than the original etching effect correction value and still less than the etching effect correction threshold, the etching liquid flow of the etching process is adjusted again until the etching effect correction value is greater than or equal to the etching effect correction threshold. If the etching liquid flow reaches the maximum value of the specified range of etching liquid flow and the etching effect correction value is still less than the etching effect correction threshold, the etching liquid pressure is adjusted. The increase of the etching liquid pressure is mapped according to the absolute difference between the etching effect correction value and the etching effect correction threshold, and the etching liquid pressure is automatically adjusted according to the increase of the etching liquid pressure.

6. A big data analysis based integrated circuit board production optimization system, characterized by, It comprises: The collection module is used for the Internet of Things gateway processor to receive the integrated circuit board production signal, collect the electrical fluctuation influence related parameters for analysis, set the light source parameters of the pattern transfer module according to the analysis result, and generate an exposure enable signal after the initial setting is completed and transmit it to the edge processor. The collection of the electrical fluctuation influence related parameters for analysis is as follows: The electrical fluctuation influence related parameters include voltage sag, harmonic distortion rate, zero ground voltage and three-phase unbalance degree. The electrical fluctuation influence coefficient is analyzed based on the electrical fluctuation influence related parameters. The electrical fluctuation influence coefficient is quantitative data of electrical fluctuation influence evaluation of voltage sag, harmonic distortion rate, zero ground voltage and three-phase unbalance degree, and the specific processing process is: proportional checking processing is performed on voltage sag, harmonic distortion rate, zero ground voltage and three-phase unbalance degree and corresponding critical values, and coupling processing is performed on the proportional checking processing result and corresponding importance score to obtain the electrical fluctuation influence coefficient; The initial setting of the light source parameters of the pattern transfer module according to the analysis result has the specific process as follows: The power range of the light source parameters is obtained from the database, the power range adjustment proportion coefficient of the light source is mapped according to the electrical fluctuation influence coefficient, the power range of the light source is adjusted according to the power range adjustment proportion coefficient of the light source, the final power range of the light source is obtained, the light source power of the pattern transfer module is adjusted to the middle value of the final power range of the light source, and the light source power of the pattern transfer module is controlled to continuously be in the final power range of the light source in the exposure stage, and the initial setting of the light source power of the pattern transfer module is completed; The exposure module: after the edge processor receives the exposure enable signal, the thickness parameter of the copper-clad plate is obtained through the thickness gauge, the exposure imaging control is optimized according to the thickness parameter of the copper-clad plate, and the etching enable signal is generated after the exposure imaging control is completed and is transmitted to the edge processor; The etching module: after the edge processor receives the etching enable signal, the etching effect evaluation related parameters are collected for analysis, the etching module is optimized in real time according to the etching analysis result, and all optimization steps and adjustment parameters are summarized to the production optimization control log and stored in the big data cloud after the etching production control is completed.

7. An electronic device, comprising: It includes: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory for executing the integrated circuit board production optimization method based on big data analysis in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, wherein the computer program enables the computer to execute the integrated circuit board production optimization method based on big data analysis in any one of claims 1 to 5.

Images